Applications · robotics

Recent work has shown that equivariant policy networks can achieve strong performance on robot manipulation tasks with limited human demonstrations. However, existing equivariant methods typically require structured inputs, such as 3D point clouds or top-down camera views, which prevents their use in low-cost setups or dynamic environments. In this work, we propose the first $\mathrm{SE}(3)$-equivariant policy learning framework that operates with only RGB image observations. The key insight is to treat image-based data as collections of rays that, unlike 2D pixels, transform under 3D roto-translations. Extensive experiments in both simulation with diverse robot configurations and real-world settings demonstrate that our method consistently surpasses strong baselines in both performance and efficiency.

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator agents (actors). The reasoner schedules targeted state probing tasks, which the evaluator agents then execute by actively interacting with the environment to collect additional observations. This enables the reasoner to assign more accurate and verifiable rewards to GUI agents. Empirical results on over 3K trajectories demonstrate that ProRe improves reward accuracy and F1 score by up to 5.3\% and 19.4\%, respectively. Furthermore, integrating ProRe with state-of-the-art policy agents yields a success rate improvement of up to 22.4\%.

High-dimensional stochastic optimal control (SOC) becomes harder with longer planning horizons: existing methods scale linearly in the horizon $T$, with performance often deteriorating exponentially. We overcome these limitations for a subclass of linearly-solvable SOC problems—those whose uncontrolled drift is the gradient of a potential. In this setting, the Hamilton-Jacobi-Bellman equation reduces to a linear PDE governed by an operator $\mathcal{L}$. We prove that, under the gradient drift assumption, $\mathcal{L}$ is unitarily equivalent to a Schrödinger operator $\mathcal{S} = -\Delta + \mathcal{V}$ with purely discrete spectrum, allowing the long-horizon control to be efficiently described via the eigensystem of $\mathcal{L}$. This connection provides two key results: first, for a symmetric linear-quadratic regulator (LQR), $\mathcal{S}$ matches the Hamiltonian of a quantum harmonic oscillator, whose closed-form eigensystem yields an analytic solution to the symmetric LQR with arbitrary terminal cost. Second, in a more general setting, we learn the eigensystem of $\mathcal{L}$ using neural networks. We identify implicit reweighting issues with existing eigenfunction learning losses that degrade performance in control tasks, and propose a novel loss function to mitigate this. We evaluate our method on several long-horizon benchmarks, achieving an order-of-magnitude improvement in control accuracy compared to state-of-the-art methods, while reducing memory usage and runtime complexity from $\mathcal{O}(Td)$ to $\mathcal{O}(d)$.

Recent advances in Bird’s Eye View (BEV) layout estimation have advanced through refinements in architectural and geometric design. However, existing methods often overlook the structured relationships among traffic elements. Components such as drivable areas, lane dividers, and pedestrian crossings constitute an interdependent system governed by civil engineering standards. For instance, stop lines precede crosswalks, which align with sidewalks, while lane dividers follow road curvature. To capture these interdependencies, we propose \textbf{ARINBEV}, an autoregressive model for BEV map estimation. Unlike prior generative approaches that rely on complex multiphase training or encoder-decoder architectures, ARINBEV employs a single-stage, decoder-only autoregressive design. This architecture enables semantically consistent BEV map estimation. On nuScenes and Argoverse2, ARINBEV attains 64.3 and 65.6 mIoU, respectively, while using $1.7\times$ fewer parameters and training $1.8\times$ faster than state-of-the-art models.

Optical flow estimation is a fundamental computer vision task that predicts per-pixel displacements from consecutive images. Recent works attempt to exploit temporal cues to improve the estimation performance. However, their temporal modeling is restricted to short video sequences due to the unaffordable computational burden, thereby suffering from restricted temporal receptive fields. Moreover, their group-wise paradigm in one forward pass undermines inter-group information exchange, leading to modest performance improvement. To address these problems, we propose a novel multi-frame optical flow network based on an auto-regressive paradigm, named ARFlow. Unlike previous multi-frame methods, our method can be scalable to arbitrary-length videos with marginal computational overhead. Specifically, we design an Auto-regressive Flow Initialization (AFI) module and an Auto-regressive Multi-stride Flow Refinement (AMFR) module to forecast the next-frame flow based on multi-stride history observations. Our ARFlow achieves state-of-the-art performance, ranking 1st on both KITTI-2015 and Spring official benchmarks and 2nd on the MPI-Sintel (Final) benchmark among all open-sourced methods. Furthermore, due to the auto-regressive nature, our method can generalize to arbitrary video length with a constant GPU memory usage of 2.1GB.

Scaling imitation learning to high-DoF whole-body robots is fundamentally limited by the \textbf{curse of dimensionality} and the prohibitive cost of collecting expert demonstrations. We argue that the core bottleneck is paradigmatic: real-world supervision for whole-body control is inherently imperfect, yet most methods assume expert data. To overcome this, we propose \textbf{HVD} (Hierarchical Value-Decomposed Offline Reinforcement Learning), an offline reinforcement learning framework that learns effective policies directly from suboptimal, reward-labeled trajectories. HVD structures the value function along the robot’s kinematic hierarchy and over temporal chunks, enabling precise credit assignment in long-horizon, high-dimensional tasks. Built on a Transformer-based architecture, HVD supports \textit{multi-modal} and \textit{multi-task} learning, allowing flexible integration of diverse sensory inputs for policy learning. To enable realistic evaluation and training, we further introduce \textbf{WB-50}, a 50-hour dataset of teleoperated and policy rollout trajectories annotated with rewards and preserving natural imperfections — including partial successes, corrections, and failures. Experiments show HVD significantly outperforms existing baselines in success rate across complex whole-body tasks. Our results suggest that effective policy learning for high-DoF systems can emerge not from perfect demonstrations, but from structured learning over realistic, imperfect data.

Non-prehensile manipulation offers a robust alternative to traditional pick-and-place methods for object repositioning. However, learning such skills with dexterous, multi-fingered hands remains largely unexplored, leaving their potential for stable and efficient manipulation underutilized. Progress has been limited by the lack of large-scale, contact-aware non-prehensile datasets for dexterous hands and the absence of wrist–finger control policies. To bridge these gaps, we present DexMove, a tactile-guided non-prehensile manipulation framework for dexterous hands. DexMove combines a scalable simulation pipeline that generates physically plausible wrist–finger trajectories with a wearable device, which captures multi-finger contact data from human demonstrations using vision-based tactile sensors. Using these data, we train a flow-based policy that enables real-time, synergistic wrist–finger control for robust non-prehensile manipulation of diverse tabletop objects. In real-world experiments, DexMove successfully manipulated six objects of varying shapes and materials, achieving a 77.8\% success rate. Our method outperforms ablated baselines by 36.6\% and improves efficiency by nearly 300\%. Furthermore, the learned policy generalizes to language-conditioned, long-horizon tasks such as object sorting and desktop tidying.

Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state--action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL.

Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate robot actions. This design allows training the planner on action-free or even non-robot data sources (e.g., videos), providing transferable high-level guidance. Nevertheless, grounding these high-level plans into executable actions remains challenging, especially with the limited availability of high-quality robot data. To this end, we propose to improve the low-level policy through online interactions. Specifically, our approach collects online rollouts, retrospectively annotates the corresponding high-level goals from achieved outcomes, and aggregates these hindsight-relabeled experiences to update a goal-conditioned imitation policy. Our method, Hindsight Flow-conditioned Online Imitation (HinFlow), instantiates this idea with 2D point flows as the high-level planner. Across diverse manipulation tasks in both simulation and physical world, our method achieves more than $2\times$ performance improvement over the base policy, significantly outperforming the existing methods. Moreover, our framework enables policy acquisition from planners trained on cross-embodiment video data, demonstrating its potential for scalable and transferable robot learning.

Learning to control high-speed objects in dynamic environments represents a fundamental challenge in robotics. Table tennis serves as an ideal testbed for advancing robotic capabilities in dynamic environments. This task presents two fundamental challenges: it requires a high-precision vision system capable of accurately predicting ball trajectories under complex dynamics, and it necessitates intelligent control strategies to ensure precise ball striking to target regions. High-speed object manipulation typically demands advanced visual perception hardware capable of capturing rapid motion with exceptional temporal resolution. Drawing inspiration from Kahneman's dual-system theory, where fast intuitive processing complements slower deliberate reasoning, there exists an opportunity to develop more robust perception architectures that can handle high-speed dynamics while maintaining accuracy. To this end, we present \textit{\textbf{SpikePingpong}}, a novel system that integrates spike-based vision with imitation learning for high-precision robotic table tennis. We develop a cognitive-inspired Fast-Slow system architecture where System 1 provides rapid ball detection and preliminary trajectory prediction with millisecond-level responses, while System 2 employs spike-oriented neural calibration for precise hittable position corrections. For strategic ball striking, we introduce Imitation-based Motion Planning And Control Technology, which learns optimal robotic arm striking policies through demonstration-based learning. Experimental results demonstrate that \textit{\textbf{SpikePingpong}} achieves a remarkable 92\% success rate for 30 cm accuracy zones and 70\% in the more challenging 20 cm precision targeting. This work demonstrates the potential of cognitive-inspired architectures for advancing robotic capabilities in time-critical manipulation tasks.

LLM-based agents have seen promising advances, yet they are still limited in “hard-exploration” tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a trajectory frontier of high-value discoveries at the global scale, while learning from local trial-and-error in exploration through a Multi-path Advantage Reflection mechanism which infers advantage-based progress signals to guide exploration. To evaluate our framework for hard-exploration, we tackle the Jericho benchmark suite of text-based games, where GLoW achieves a new state-of-the-art performance for LLM-based approaches. Compared to state-of-the-art RL-based methods, our approach achieves comparable performance while requiring 100-800× fewer environment interactions.

Differentiable model predictive control (MPC) offers a powerful framework for combining learning and control. However, its adoption has been limited by the inherently sequential nature of traditional optimization algorithms, which are challenging to parallelize on modern computing hardware like GPUs. In this work, we tackle this bottleneck by introducing a GPU-accelerated differentiable optimization tool for MPC. This solver leverages sequential quadratic programming and a custom preconditioned conjugate gradient (PCG) routine with tridiagonal preconditioning to exploit the problem's structure and enable efficient parallelization. We demonstrate substantial speedups over CPU- and GPU-based baselines, significantly improving upon state-of-the-art training times on benchmark reinforcement learning and imitation learning tasks. Finally, we showcase the method on the challenging task of reinforcement learning for driving at the limits of handling, where it enables robust drifting of a Toyota Supra through water puddles.

Scaling visual geometry transformers for long image sequences poses a significant computational and memory challenge. In this work, we diagnose this issue in the state-of-the-art model VGGT, and trace the primary bottleneck to its Global Attention layer. Our analysis reveals a ``token collapse'' phenomenon, where many tokens attend to nearly identical regions, resulting in redundant computation and inefficiency. Motivated by this finding, we propose FastVGGT, a training-free framework that strategically prunes these redundant tokens. Instead of uniform merging, FastVGGT employs a tailored, three-part token partitioning strategy. It preserves initial-frame tokens as a stable global reference, retains salient tokens to maintain fine details, and utilizes region-based random sampling to ensure spatially balanced coverage. Extensive experiments on multiple 3D geometry benchmarks validate our approach's effectiveness. Notably, on sequences of 1000 images, FastVGGT achieves a 4$\times$ speedup over the original VGGT while simultaneously mitigating error accumulation, demonstrating its efficiency and robustness for long-sequence scenarios. For further details, please visit our project page: https://fastvggt.github.io/.

Deep Reinforcement Learning has achieved remarkable progress in solving NP-hard scheduling problems. However, existing methods primarily focus on optimizing average performance over training instances, overlooking the core objective of solving each individual instance with high quality. While several instance-wise adaptation mechanisms have been proposed, they are test-time approaches only and cannot share knowledge across different adaptation tasks. Moreover, they largely rely on gradient-based optimization, which could be ineffective in dealing with combinatorial optimization problems. We address the above issues by proposing an instance-wise meta-learning framework. It trains a meta model to acquire a generalizable initialization that effectively guides per-instance adaptation during inference, and overcomes the limitations of gradient-based methods by leveraging a derivative-free optimization scheme that is fully GPU parallelizable. Experimental results on representative scheduling problems demonstrate that our method consistently outperforms existing learning-based scheduling methods and instance-wise adaptation mechanisms under various task sizes and distributions.

Hierarchical coarse-to-fine policy, where a coarse branch predicts a region of interest to guide a fine-grained action predictor, has demonstrated significant potential in robotic 3D manipulation tasks by especially enhancing sample efficiency and enabling more precise manipulation. However, even augmented with pre-trained models, these hierarchical policies still suffer from generalization issues. To enhance generalization to novel instructions and environment variations, we propose Coarse-to-fine Language-Aligned manipulation Policy (CLAP), a framework that integrates three key components: 1) task decomposition, 2) VLM fine-tuning for 3D keypoint prediction, and 3) 3D-aware representation. Through comprehensive experiments in simulation and on a real robot, we demonstrate its superior generalization capability. Specifically, on GemBench, a benchmark designed for evaluating generalization, our approach achieves a 12\% higher average success rate than the SOTA method while using only 1/5 of the training trajectories. In real-world experiments, our policy, trained on only 10 demonstrations, successfully generalizes to novel instructions and environments.

The co-design of robot morphology and neural control typically requires using reinforcement learning to approximate a unique control policy gradient for each body plan, demanding massive amounts of training data to measure the performance of each design. Here we show that a universal, morphology-agnostic controller can be rapidly and directly obtained by gradient-based optimization through differentiable simulation. This process of morphological pretraining allows the designer to explore non-differentiable changes to a robot's physical layout (e.g. adding, removing and recombining discrete body parts) and immediately determine which revisions are beneficial and which are deleterious using the pretrained model. We term this process "zero-shot evolution" and compare it with the simultaneous co-optimization of a universal controller alongside an evolving design population. We find the latter results in _diversity collapse_, a previously unknown pathology whereby the population—and thus the controller's training data—converges to similar designs that are easier to steer with a shared universal controller. We show that zero-shot evolution with a pretrained controller quickly yields a diversity of highly performant designs, and by fine-tuning the pretrained controller on the current population throughout evolution, diversity is not only preserved but significantly increased as superior performance is achieved. Videos viewable at this website: https://gilded-macaron-5a75e3.netlify.app

We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to changes in visual appearance. We address key limitations of recent methods, such as the lack of uncertainty modeling in depth predictions and the necessity for custom depth networks trained for each environment. We introduce a novel probabilistic model that incorporates uncertainty estimation, modeling depth predictions as explicit probability distributions. By leveraging off-the-shelf pre-trained monocular depth models, we eliminate the need to rely on per-environment-trained depth networks, enhancing generalization to unseen spaces. We evaluate UnLoc on large-scale synthetic and real-world datasets, demonstrating significant improvements over existing methods in terms of accuracy and robustness. Notably, we achieve $2.7$ times higher localization recall on long sequences (100 frames) and $42.2$ times higher on short ones (15 frames) than the state of the art on the challenging LaMAR HGE dataset.

Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge as lifelong embodied navigation learning (LENL), where an agent is required to adapt to a sequence of navigation tasks spanning multiple scenes and diverse user instruction styles, while retaining previously learned knowledge. To tackle this problem, we propose Uni-Walker, a lifelong embodied navigation framework that decouples navigation knowledge into task-shared and task-specific components with Decoder Extension LoRA (DE-LoRA). To learn the shared knowledge, we design a knowledge inheritance strategy and an experts co-activation strategy to facilitate shared knowledge transfer and refinement across multiple navigation tasks. To learn the specific knowledge, we propose an expert subspace orthogonality constraint together and a navigation-specific chain-of-thought reasoning mechanism to capture specific knowledge and enhance instruction-style understanding. Extensive experiments demonstrate the superiority of Uni-Walker for building universal embodied navigation agents with lifelong learning. We also provide the code of this work in the Supplementary Materials.

Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the underlying kinematic structure of articulated systems. To this end, we propose the **Neural Rodrigues Operator**, a learnable generalization of the classical forward kinematics operation, designed to inject kinematics-aware inductive bias into neural computation. Building on this operator, we design the **Rodrigues Network (RodriNet)**, a novel neural architecture specialized for processing actions. We evaluate the expressivity of our network on two synthetic tasks on kinematic and motion prediction, showing significant improvements compared to standard backbones. We further demonstrate its effectiveness in two realistic applications: (i) imitation learning on robotic benchmarks with the Diffusion Policy, and (ii) single-image 3D hand reconstruction. Our results suggest that integrating structured kinematic priors into the network architecture improves action learning in various domains.

The ability to conduct and learn from self-directed interaction and experience is a central challenge in robotics, offering a scalable alternative to labor-intensive human demonstrations. However, realizing such "play" requires (1) a policy robust to diverse, potentially out-of-distribution environment states, and (2) a procedure that continuously produces useful, task-directed robot experience. To address these challenges, we introduce Tether, a method for autonomous play with two key contributions. First, we design a novel non-parametric policy that leverages strong visual priors for extreme generalization: given two-view images, it identifies semantic correspondences to warp demonstration trajectories into new scenes. We show that this design is robust to significant spatial and semantic variations of the environment, such as dramatic positional differences and unseen objects. We then deploy this policy for autonomous multi-task play in the real world via a continuous cycle of task selection, execution, evaluation, and improvement, guided by the visual understanding capabilities of vision-language models. This procedure generates diverse, high-quality datasets with minimal human intervention. In a household-like multi-object setup, our method is among the first to perform many hours of autonomous real-world play, producing a stream of data that consistently improves downstream policy performance over time. Ultimately, Tether yields over 1000 expert-level trajectories and trains policies competitive with those learned from human-collected demonstrations.